Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to academic policies and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¢ãĥ¼
    -0.17
    èĩ
    -0.16
    mada
    -0.15
     Fres
    -0.15
    -neutral
    -0.15
    åľĨ
    -0.14
     neutral
    -0.14
    neutral
    -0.14
    wy
    -0.14
     introductory
    -0.14
    POSITIVE LOGITS
     transcript
    0.25
     advising
    0.22
     Transcript
    0.22
     Advis
    0.22
     Withdraw
    0.22
     Dro
    0.21
     Drops
    0.21
     transcripts
    0.20
     course
    0.20
     withdrawal
    0.20
    Act Density 0.033%

    No Known Activations